gbanyan 8f231da3bc Complete OpenCV Method 3 implementation with 86.5% handwriting retention ...

- Implemented comprehensive feature analysis based on size, stroke length, and regularity
- Size-based scoring: height >50px indicates handwriting
- Stroke length ratio: >0.4 indicates handwriting
- Irregularity metrics: low compactness/solidity indicates handwriting
- Successfully tested on sample PDF with 2 signatures (楊智惠, 張志銘)
- Created detailed documentation: CURRENT_STATUS.md and NEW_SESSION_HANDOFF.md
- Stable PaddleOCR 2.7.3 configuration documented (numpy 1.26.4, opencv 4.6.0.66)
- Prepared research plan for PP-OCRv5 upgrade investigation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

2025-11-27 10:35:46 +08:00

9.0 KiB

Raw Blame History

View Raw